Yntec commited on
Commit
6cde45c
1 Parent(s): 61552a5

Adding `diffusers` weights of this model (#2)

Browse files

- Adding `diffusers` weights of this model (7585ab348c0a56e7ee7260764224f9f16409dc0e)

model_index.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.14.0.dev0",
4
  "feature_extractor": [
5
  "transformers",
6
  "CLIPFeatureExtractor"
7
  ],
8
- "requires_safety_checker": null,
9
  "safety_checker": [
10
- null,
11
- null
12
  ],
13
  "scheduler": [
14
  "diffusers",
 
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.18.0.dev0",
4
  "feature_extractor": [
5
  "transformers",
6
  "CLIPFeatureExtractor"
7
  ],
8
+ "requires_safety_checker": true,
9
  "safety_checker": [
10
+ "stable_diffusion",
11
+ "StableDiffusionSafetyChecker"
12
  ],
13
  "scheduler": [
14
  "diffusers",
safety_checker/config.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "cb41f3a270d63d454d385fc2e4f571c487c253c5",
3
+ "_name_or_path": "CompVis/stable-diffusion-safety-checker",
4
+ "architectures": [
5
+ "StableDiffusionSafetyChecker"
6
+ ],
7
+ "initializer_factor": 1.0,
8
+ "logit_scale_init_value": 2.6592,
9
+ "model_type": "clip",
10
+ "projection_dim": 768,
11
+ "text_config": {
12
+ "_name_or_path": "",
13
+ "add_cross_attention": false,
14
+ "architectures": null,
15
+ "attention_dropout": 0.0,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 0,
19
+ "chunk_size_feed_forward": 0,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "dropout": 0.0,
25
+ "early_stopping": false,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 2,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "hidden_act": "quick_gelu",
33
+ "hidden_size": 768,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_factor": 1.0,
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "is_decoder": false,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "layer_norm_eps": 1e-05,
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "max_position_embeddings": 77,
51
+ "min_length": 0,
52
+ "model_type": "clip_text_model",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 12,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 12,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": 1,
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "projection_dim": 512,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "sep_token_id": null,
72
+ "suppress_tokens": null,
73
+ "task_specific_params": null,
74
+ "temperature": 1.0,
75
+ "tf_legacy_loss": false,
76
+ "tie_encoder_decoder": false,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_class": null,
79
+ "top_k": 50,
80
+ "top_p": 1.0,
81
+ "torch_dtype": null,
82
+ "torchscript": false,
83
+ "transformers_version": "4.30.2",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "vocab_size": 49408
87
+ },
88
+ "torch_dtype": "float16",
89
+ "transformers_version": null,
90
+ "vision_config": {
91
+ "_name_or_path": "",
92
+ "add_cross_attention": false,
93
+ "architectures": null,
94
+ "attention_dropout": 0.0,
95
+ "bad_words_ids": null,
96
+ "begin_suppress_tokens": null,
97
+ "bos_token_id": null,
98
+ "chunk_size_feed_forward": 0,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "dropout": 0.0,
104
+ "early_stopping": false,
105
+ "encoder_no_repeat_ngram_size": 0,
106
+ "eos_token_id": null,
107
+ "exponential_decay_length_penalty": null,
108
+ "finetuning_task": null,
109
+ "forced_bos_token_id": null,
110
+ "forced_eos_token_id": null,
111
+ "hidden_act": "quick_gelu",
112
+ "hidden_size": 1024,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "image_size": 224,
118
+ "initializer_factor": 1.0,
119
+ "initializer_range": 0.02,
120
+ "intermediate_size": 4096,
121
+ "is_decoder": false,
122
+ "is_encoder_decoder": false,
123
+ "label2id": {
124
+ "LABEL_0": 0,
125
+ "LABEL_1": 1
126
+ },
127
+ "layer_norm_eps": 1e-05,
128
+ "length_penalty": 1.0,
129
+ "max_length": 20,
130
+ "min_length": 0,
131
+ "model_type": "clip_vision_model",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 16,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_channels": 3,
137
+ "num_hidden_layers": 24,
138
+ "num_return_sequences": 1,
139
+ "output_attentions": false,
140
+ "output_hidden_states": false,
141
+ "output_scores": false,
142
+ "pad_token_id": null,
143
+ "patch_size": 14,
144
+ "prefix": null,
145
+ "problem_type": null,
146
+ "projection_dim": 512,
147
+ "pruned_heads": {},
148
+ "remove_invalid_values": false,
149
+ "repetition_penalty": 1.0,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "sep_token_id": null,
153
+ "suppress_tokens": null,
154
+ "task_specific_params": null,
155
+ "temperature": 1.0,
156
+ "tf_legacy_loss": false,
157
+ "tie_encoder_decoder": false,
158
+ "tie_word_embeddings": true,
159
+ "tokenizer_class": null,
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "torch_dtype": null,
163
+ "torchscript": false,
164
+ "transformers_version": "4.30.2",
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false
167
+ }
168
+ }
safety_checker/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08902f19b1cfebd7c989f152fc0507bef6898c706a91d666509383122324b511
3
+ size 608018440
safety_checker/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11cfe53105625af8c00faac32a430626641cce686454f3c39d837f14397d858b
3
+ size 1215981832
safety_checker/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
3
+ size 1216064769
safety_checker/pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ba87205445ad5def13e54919b038dcfb7321ec1c3f4b12487d4fba6036125f
3
+ size 608103564
scheduler/scheduler_config.json CHANGED
@@ -1,14 +1,20 @@
1
  {
2
  "_class_name": "PNDMScheduler",
3
- "_diffusers_version": "0.14.0.dev0",
4
  "beta_end": 0.012,
5
  "beta_schedule": "scaled_linear",
6
  "beta_start": 0.00085,
7
  "clip_sample": false,
 
 
8
  "num_train_timesteps": 1000,
9
  "prediction_type": "epsilon",
 
 
10
  "set_alpha_to_one": false,
11
  "skip_prk_steps": true,
12
  "steps_offset": 1,
 
 
13
  "trained_betas": null
14
  }
 
1
  {
2
  "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.18.0.dev0",
4
  "beta_end": 0.012,
5
  "beta_schedule": "scaled_linear",
6
  "beta_start": 0.00085,
7
  "clip_sample": false,
8
+ "clip_sample_range": 1.0,
9
+ "dynamic_thresholding_ratio": 0.995,
10
  "num_train_timesteps": 1000,
11
  "prediction_type": "epsilon",
12
+ "rescale_betas_zero_snr": false,
13
+ "sample_max_value": 1.0,
14
  "set_alpha_to_one": false,
15
  "skip_prk_steps": true,
16
  "steps_offset": 1,
17
+ "thresholding": false,
18
+ "timestep_spacing": "leading",
19
  "trained_betas": null
20
  }
text_encoder/config.json CHANGED
@@ -19,7 +19,7 @@
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.26.1",
24
  "vocab_size": 49408
25
  }
 
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.30.2",
24
  "vocab_size": 49408
25
  }
tokenizer/tokenizer_config.json CHANGED
@@ -8,6 +8,7 @@
8
  "rstrip": false,
9
  "single_word": false
10
  },
 
11
  "do_lower_case": true,
12
  "eos_token": {
13
  "__type": "AddedToken",
@@ -19,9 +20,7 @@
19
  },
20
  "errors": "replace",
21
  "model_max_length": 77,
22
- "name_or_path": "openai/clip-vit-large-patch14",
23
  "pad_token": "<|endoftext|>",
24
- "special_tokens_map_file": "./special_tokens_map.json",
25
  "tokenizer_class": "CLIPTokenizer",
26
  "unk_token": {
27
  "__type": "AddedToken",
 
8
  "rstrip": false,
9
  "single_word": false
10
  },
11
+ "clean_up_tokenization_spaces": true,
12
  "do_lower_case": true,
13
  "eos_token": {
14
  "__type": "AddedToken",
 
20
  },
21
  "errors": "replace",
22
  "model_max_length": 77,
 
23
  "pad_token": "<|endoftext|>",
 
24
  "tokenizer_class": "CLIPTokenizer",
25
  "unk_token": {
26
  "__type": "AddedToken",
unet/config.json CHANGED
@@ -1,7 +1,9 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.14.0.dev0",
4
  "act_fn": "silu",
 
 
5
  "attention_head_dim": 8,
6
  "block_out_channels": [
7
  320,
@@ -11,9 +13,11 @@
11
  ],
12
  "center_input_sample": false,
13
  "class_embed_type": null,
 
14
  "conv_in_kernel": 3,
15
  "conv_out_kernel": 3,
16
  "cross_attention_dim": 768,
 
17
  "down_block_types": [
18
  "CrossAttnDownBlock2D",
19
  "CrossAttnDownBlock2D",
@@ -22,21 +26,29 @@
22
  ],
23
  "downsample_padding": 1,
24
  "dual_cross_attention": false,
 
 
25
  "flip_sin_to_cos": true,
26
  "freq_shift": 0,
27
  "in_channels": 4,
28
  "layers_per_block": 2,
 
29
  "mid_block_scale_factor": 1,
30
  "mid_block_type": "UNetMidBlock2DCrossAttn",
31
  "norm_eps": 1e-05,
32
  "norm_num_groups": 32,
 
33
  "num_class_embeds": null,
34
  "only_cross_attention": false,
35
  "out_channels": 4,
36
  "projection_class_embeddings_input_dim": null,
 
 
37
  "resnet_time_scale_shift": "default",
38
  "sample_size": 64,
39
  "time_cond_proj_dim": null,
 
 
40
  "time_embedding_type": "positional",
41
  "timestep_post_act": null,
42
  "up_block_types": [
@@ -45,6 +57,6 @@
45
  "CrossAttnUpBlock2D",
46
  "CrossAttnUpBlock2D"
47
  ],
48
- "upcast_attention": false,
49
  "use_linear_projection": false
50
  }
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.18.0.dev0",
4
  "act_fn": "silu",
5
+ "addition_embed_type": null,
6
+ "addition_embed_type_num_heads": 64,
7
  "attention_head_dim": 8,
8
  "block_out_channels": [
9
  320,
 
13
  ],
14
  "center_input_sample": false,
15
  "class_embed_type": null,
16
+ "class_embeddings_concat": false,
17
  "conv_in_kernel": 3,
18
  "conv_out_kernel": 3,
19
  "cross_attention_dim": 768,
20
+ "cross_attention_norm": null,
21
  "down_block_types": [
22
  "CrossAttnDownBlock2D",
23
  "CrossAttnDownBlock2D",
 
26
  ],
27
  "downsample_padding": 1,
28
  "dual_cross_attention": false,
29
+ "encoder_hid_dim": null,
30
+ "encoder_hid_dim_type": null,
31
  "flip_sin_to_cos": true,
32
  "freq_shift": 0,
33
  "in_channels": 4,
34
  "layers_per_block": 2,
35
+ "mid_block_only_cross_attention": null,
36
  "mid_block_scale_factor": 1,
37
  "mid_block_type": "UNetMidBlock2DCrossAttn",
38
  "norm_eps": 1e-05,
39
  "norm_num_groups": 32,
40
+ "num_attention_heads": null,
41
  "num_class_embeds": null,
42
  "only_cross_attention": false,
43
  "out_channels": 4,
44
  "projection_class_embeddings_input_dim": null,
45
+ "resnet_out_scale_factor": 1.0,
46
+ "resnet_skip_time_act": false,
47
  "resnet_time_scale_shift": "default",
48
  "sample_size": 64,
49
  "time_cond_proj_dim": null,
50
+ "time_embedding_act_fn": null,
51
+ "time_embedding_dim": null,
52
  "time_embedding_type": "positional",
53
  "timestep_post_act": null,
54
  "up_block_types": [
 
57
  "CrossAttnUpBlock2D",
58
  "CrossAttnUpBlock2D"
59
  ],
60
+ "upcast_attention": null,
61
  "use_linear_projection": false
62
  }
unet/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57816bec8909cc7009dd50e26ebede2f1515147e80125477c93b81340f19fa5c
3
  size 3438366373
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da3830839f9c5e6dc97c30dab18b9d3a487bcbb96987e3a65a72819d12ab1e06
3
  size 3438366373
unet/diffusion_pytorch_model.fp16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1d3768373ad0c46c902acb41f5558c47e87d1c7b00140e407058229ae5b6f5f
3
  size 1719327893
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d904bd66843280d5c40e0bb22abda4bdadcf123e2ba00db78899b9dfc06f5016
3
  size 1719327893
unet/diffusion_pytorch_model.fp16.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bb7b712815a1a6f227cb36f5e912a7e951270343c2b2a0734fa832136f29873
3
  size 1719125304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1901d1cc8255889481cd0d1964ee35c662e7c987c514d9ef4617fcbfb5b26de0
3
  size 1719125304
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a78af4da33e537d634d0a89becdb412dead657682aed8c7062fdeff2c2dafdf0
3
  size 3438167536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c55ee3d1cac2790c2fea9a0ec02702aa3ac812ef0a415b4b88bb157437d0a72
3
  size 3438167536
vae/config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.14.0.dev0",
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
@@ -28,4 +28,3 @@
28
  "UpDecoderBlock2D"
29
  ]
30
  }
31
-
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.18.0.dev0",
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
 
28
  "UpDecoderBlock2D"
29
  ]
30
  }
 
vae/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31fef5fa5b3814b08002682045f776fc951ba2dacec7af6807018189516b121f
3
  size 334712113
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97247721f0146ed047837593fc9fcec39b15cc418227b9ab7a4c83fbf062af68
3
  size 334712113
vae/diffusion_pytorch_model.fp16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d207e4928394a2002bcb7fff829e93bbd2a44bc323e597fdb690d3fc2d064de2
3
  size 167405651
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e39f5b86938675e51efdaa8e034e7961828a14f921ca76db96526ce454a02d03
3
  size 167405651
vae/diffusion_pytorch_model.fp16.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d8fb415ab4f9782232e7bb82e618e2c0cef0be3593c77a35f5733d8fdd3530f
3
  size 167335342
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:992a16290de9d7d4c6c4ebb6049f539e6e5bdbe5ab7a87c724d9f029ada64fc6
3
  size 167335342
vae/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e91305cd81f7d1387694a231b63de771190b3f2c25591eb71a8c2525cb08397
3
  size 334643268
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f70a07979060887ec01da7cb1bfc97f298f8079ded5a20cb5895976f3bcacd26
3
  size 334643268